Research Methods & Data AnalysisRepresentative program

AI Unlocked: Data, Uncertainty, and Smart Decision-Making

Compare predictive models and examine how uncertainty changes the interpretation of data-driven decisions.

Overview

Using Python or R, learners build and compare predictive models for a carefully scoped application. The program combines regression, decision trees, and introductory Bayesian reasoning with model validation and uncertainty analysis. Examples may draw on environmental, housing, or financial datasets; predictions are evaluated as research outputs, not decision guarantees.

Learning goals and possible work

Proposed learning outcomes for this program example:

  • Build and compare transparent baseline and machine-learning models.
  • Evaluate errors using appropriate data splits and metrics.
  • Communicate model uncertainty and implications for a bounded use case.

Illustrative learning sequence

The sequence below illustrates how this program’s content can be organized. Topics, pacing, and project depth are adapted for each offering. This is not an archived record of a specific cohort’s weekly syllabus.

  1. 01Prediction questions and decisions under uncertainty
  2. 02Data preparation and exploratory analysis
  3. 03Regression models as transparent baselines
  4. 04Classification and decision trees
  5. 05Training, validation, and test design
  6. 06Comparing models and diagnosing error
  7. 07Foundations of Bayesian reasoning
  8. 08Uncertainty intervals and sensitivity to assumptions
  9. 09Evaluating a chosen application and documenting limitations
  10. 10Presenting a reproducible model-comparison study
Ask About This Program Back to the Program Portfolio

Related program examples